Equivalence between dropout and data augmentation: A mathematical check

The great achievements of deep learning can be attributed to its tremendous power of feature representation, where the representation ability comes from the nonlinear activation function and the large number of network nodes. However, deep neural networks suffer from serious issues such as slow conv...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Neural networks 2019-07, Vol.115, p.82-89
Hauptverfasser:	Zhao, Dazhi, Yu, Guozhu, Xu, Peng, Luo, Maokang
Format:	Artikel
Sprache:	eng
Schlagworte:	Data augmentation Deep learning Dropout Mathematical check Neural network
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!